论文标题
具有修改后的RELU网络的非参数回归
Nonparametric regression with modified ReLU networks
论文作者
论文摘要
我们考虑使用修改后的Relu神经网络进行回归估计，其中首先通过函数$α$修改网络权重矩阵，然后再乘以输入向量。我们举例说明了连续的，分段线性函数$α$，以使用$ l_1 $的经验风险最小化的经验风险最小化器，并平方$ l_2 $ noperties，最多可对数因素，最小值的预测$β$ -S-Sm-Sm-SmortOl-s-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Sm-Smompooth Function。
We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function $α$ before being multiplied by input vectors. We give an example of continuous, piecewise linear function $α$ for which the empirical risk minimizers over the classes of modified ReLU networks with $l_1$ and squared $l_2$ penalties attain, up to a logarithmic factor, the minimax rate of prediction of unknown $β$-smooth function.
